Can you get SoTA results on 4 various point cloud processing tasks with a single block? The answer is yes! 🌐Project page: saic-violet.github.io/cloud-transfor… 📽️Video: youtu.be/lYTzLhy-ybw 🧐Paper: arxiv.org/abs/2007.11679 Join us on Session 8b at #ICCV21 on Oct 15th

Our work on leveraging general pre-trained feature extractors for open-set real-time scene understanding has been accepted for #ICRA2023! Joint work with Edgar Sucar Andrew Davison Check out project page: makezur.github.io/FeatureRealist…

Should the complexity of 3D reconstruction tasks be dependent on # of pixels or # of “things” in the image? We use surface normal and segmentation priors to split the image into 2.5D segments and show how this representation can help tackle a wide range of 3D reconstruction tasks

Survival of the fittest!

SuperPrimitives got accepted to #CVPR2024! The code will be released soon and see you all in Seattle!

Code release for SuperPrimitives, and it comes with an interactive GUI! #CVPR2024 github.com/makezur/super_… SuperPrimitive is a new 3D representation which enables solving many 3D tasks at the level of image segments.

How can we infer 3D-consistent poses and dense geometry in real-time given only RGB images? 𝗖𝗢𝗠𝗢 decodes dense geometry from a compact and optimizable set of 3D anchor points to enforce 3D consistency. Project page: edexheim.github.io/como/ Work with Andrew Davison 1/n

SuperPrimitives will be presented at #CVPR next week (Wednesday), along with a 𝗿𝗲𝗮𝗹-𝘁𝗶𝗺𝗲 𝗱𝗲𝗺𝗼 on Friday! Our new representation enables dense monocular 3D reconstruction in real-time. No poses required! Project page: makezur.github.io/SuperPrimitive/

Curious how DSINE surface normals can be converted into full 3D geometry? Visit our demo of 𝗦𝘂𝗽𝗲𝗿𝗣𝗿𝗶𝗺𝗶𝘁𝗶𝘃𝗲-based real-time 3D reconstruction tomorrow (Friday)! A demo is worth a thousand pictures 🙂 Demo: 10:30 to 18:45, Arch CDE #9 #CVPR #CVPR2024

Introducing MASt3R-SLAM, the first real-time monocular dense SLAM with MASt3R as a foundation. Easy to use like DUSt3R/MASt3R, from an uncalibrated RGB video it recovers accurate, globally consistent poses & a dense map. With Eric Dexheimer*, Andrew Davison (*Equal Contribution)